Run frontier-class models. 70B+ parameter LLMs at native precision. Multi-modal vision, audio, and reasoning models — all on-device, all real-time, all yours.
Workstation-class AI supercomputer
Power Your Swarm.
Run flagship-tier models, host swarms, and operate as a primary node in the machine economy. Pro-tier NPU + dual GPU config.
Estimated delivery: Q1 2026.
Workstation-class. Network-native.
Everything the data center promises. None of the lock-in.
Anchor a swarm. Coordinate dozens of leased nodes from a single Pro. Schedule workloads, route inference, settle in XE — your edge cluster, your terms.
Serve agents at scale. Pro-class throughput for high-frequency agent calls. Publish endpoints with attested hardware and earn premium reputation tiers.
Settle the network. Run a relay node. Validate transactions. Earn settlement fees on every cycle of the open compute market.
Eight SSD slots. Up to 64 TB.
Eight tool-less M.2 bays with RAID-Z2 across all of them. Hot-swap, encryption at rest, snapshot rollback. Infrastructure storage on your desk.
Aluminum monolith.
Single-block aluminum chassis, scaled up. Liquid cooling routes through the structural members — no fans audible at desk-distance, no thermal throttling under sustained load.
Validator-grade resilience.
Dual redundant power, ECC throughout, on-chain attested boot. Designed to run as a primary node in the network — uptime and integrity are first-class.
Magnetic lid for tool-less swaps.
Same one-motion lid. The Pro routes thermal pads to two heat-pipes for sustained workstation loads — keeping the SSDs cool no matter how long the inference run.
01 / 04
Built for swarms
Edge-native primitives, at infrastructure scale.
Coordinator-class throughput for fleets of agents. Every protocol, every endpoint — designed for machines that talk to other machines.
Agent-to-agent comms.
Sub-millisecond encrypted messaging across leased nodes. No middleman, no metadata leakage, no rate limits.
Settlement at swarm scale.
Settle every inference, lease, and call in XE on-chain — at thousands of transactions per second.
Validator endpoints.
Anchor identity for the entire swarm. Other agents discover and trust your nodes via on-chain attestation.
Structured-data first.
JSON alternates on every page, Pro-tier observability — agents can parse, cite, and audit you in real time.
Powered by XE OS Pro
The operating system for sovereign infrastructure.
Workstation features. Pro tier unlocks swarm coordinator, relay node, and validator modes alongside everything in standard XE OS.
Swarm coordinator.
Schedule inference across owned and leased nodes. Watch latency and cost trade off in real time. Cap budgets per agent.
Relay-grade storage.
RAID-Z2 across eight bays. Hot-swap, encryption at rest, snapshot rollback. Infrastructure storage on your desk.
Validator mode.
Run a full XE node. Validate transactions, earn settlement fees, contribute to network finality.
Pro app catalog.
Production-grade Postgres, ClickHouse, Vespa, vLLM. Sandbox isolation with IO QoS so workloads don't trample each other.
Off-site replication.
Continuous encrypted backups to other XE Devices, S3-compatible buckets, or cold storage. Restore at any point in time.
Beautifully simple.
Same five-minute setup. Same one-click install. Pro's complexity hides behind an interface you already know how to use.
Same setup. Pro hardware.
Five minutes from unbox to swarm.
Built for the network
The specs that matter.
16 cores
Intel® i9 + discrete GPU
64 TB
Max NVMe storage · 8 slots
10 GbE
SFP+ · WiFi 6E · BT 5.3
32 GB
ECC LPDDR5
70B+ params
Frontier-tier inference
28 W
Active cooling · liquid loop
Everything you need
All the right connections.
Which XE Device is right for you?
Two sovereign nodes. One perfect fit.
XE Device Pro
NewWorkstation-class compute for swarm coordination and frontier-tier inference.
Reserve XE Device ProInference
Up to 37B params
Mid-tier LLMs on-device
Up to 70B+ params
Frontier LLMs with dedicated VRAM
Chip
Intel® N150
4 cores · 3.6 GHz
Intel® Core™ i3-N300
8 cores · 3.8 GHz
NPU
Dedicated
On-device matrix engine
Pro NPU + GPU
Dual accelerator config
VMs
~20 simultaneous
QEMU-backed isolation
~80 simultaneous
Pro virtualization stack
Memory
16 GB
LPDDR5
32 GB
LPDDR5
Network
2.5 GbE
RJ45 · WiFi 6
10 GbE
SFP+ · WiFi 6E
Power
7 W TDP
Fanless, idle 4 W
28 W TDP
Active cooling
Swarm
Joins
Contributes spare cycles
Anchors
Coordinates leased nodes
Open source
CAD + OS
Fully published
CAD + OS Pro
Fully published
Questions? Answers.
Everything you need to know about the XE Device.
No. Plug it in, connect to your network, and visit `xe.local` in your browser. The OS guides you through identity setup, key generation, and joining the network — typically under five minutes.
The XE Device runs models up to ~37B parameters comfortably (e.g. Llama 3 70B Q4, Mistral Nemo, Qwen 3 32B). The Pro extends that to 70B+ at native precision with dedicated VRAM.
No, by default. Inference, files, and agent state stay on your hardware. You can opt into network features (relay rewards, swarm leasing) per-app — each one explicit, encrypted, and revocable.
Built-in cryptographic backup runs continuously to a USB drive, NAS, or another XE Device. RAID-aware Failsafe Mode keeps you running through any single-drive failure with no data loss.
When the device is idle, it can opt into the open swarm and accept inference / VM jobs. Settled in XE on completion, on-chain. You set your hourly rate and a cap.
Yes. The XE App Store ships with 200+ self-hostable apps (Ollama, Immich, Postgres, …). Each runs sandboxed under XE OS — your other apps and files are protected.
Yes. Schematics, CAD, BOM, and the full OS source are published under permissive licences. You can fork, modify, or build your own from scratch.
Estimated delivery is Q4 2025 for the XE Device and Q1 2026 for the XE Device Pro. Reserve with 1 XE token (5 for the Pro) to lock your position.